Instructions to use huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle3

tokenizer = AutoTokenizer.from_pretrained("huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810")
model = LlamaForCausalLMEagle3.from_pretrained("huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810

SGLang

How to use huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810 with Docker Model Runner:
```
docker model run hf.co/huluhuluu/llama3p2-3b-inst-eagle3-sharegpt-sw512-epoch-9-step-231810
```

Llama-3.2 3b Instruct EAGLE3 ShareGPT SW512

This repository contains a SpecForge EAGLE3 draft-model checkpoint for use with meta-llama/Llama-3.2-3B-Instruct. It is a draft model for speculative decoding, not a standalone target language model.

Checkpoint

Field	Value
Source run	`llama3.2-3b-inst-eagle3-sharegpt-sw512`
Checkpoint	`epoch_9_step_231810`
Epoch	`9`
Global step	`231810`
Files	`config.json`, `model.safetensors`, `training_state.pt` (when present)

Training Parameters

Parameter	Value
Base model	`meta-llama/Llama-3.2-3B-Instruct`
Method	`SpecForge EAGLE3 online training`
Training data	`sharegpt_train_clean.jsonl`
Learning rate	`0.0001`
Batch size	`1`
Target batch size	`1`
Epochs configured	`10`
Max length	`2048`
Warmup ratio	`0.015`
Max grad norm	`0.5`
TTT length	`7`
Draft layers	`Not recorded`
Draft sliding window	`512`
Save interval	`5000`
Eval interval	`5000`
Seed	`0`
TP / DP size	`1 / 4`
Attention backend	`sdpa`
Target model backend	`sglang`
SGLang attention backend	`flashinfer`
Dataset build workers	`64`

Draft Model Configuration

Field	Value
Architecture	`LlamaForCausalLMEagle3`
dtype	`bfloat16`
Hidden size	`3072`
Intermediate size	`8192`
Draft layers	`1`
Attention heads	`24`
KV heads	`8`
Draft vocab size	`32000`
Vocab size	`128256`
Max position embeddings	`131072`
Sliding window	`512`
Max window layers	`Not recorded`
Future hidden	`Not recorded`

Notes

This is the highest-step local checkpoint available when this repository was published.
The checkpoint is intended to be loaded by SpecForge/EAGLE3-compatible code.
training_state.pt is included when available for provenance and training-state inspection.
No benchmark claim is made in this card.